A data‐driven algorithm for constructing artificial neural network rainfall‐runoff models

TLDR

The study proposes a data‑driven method for designing the network architecture of an ANN‑based rainfall‑runoff model. The method selects an optimal input vector by exploiting cross‑, auto‑, and partial‑auto‑correlation statistics and trains the network with a standard algorithm, validated on an Indian river basin dataset. Results show the approach is promising, potentially cutting development effort and computational time for ANN models. © 2002 John Wiley & Sons, Ltd.

Abstract

Abstract A new approach for designing the network structure in an artificial neural network (ANN)‐based rainfall‐runoff model is presented. The method utilizes the statistical properties such as cross‐, auto‐ and partial‐auto‐correlation of the data series in identifying a unique input vector that best represents the process for the basin, and a standard algorithm for training. The methodology has been validated using the data for a river basin in India. The results of the study are highly promising and indicate that it could significantly reduce the effort and computational time required in developing an ANN model. Copyright © 2002 John Wiley & Sons, Ltd.